INDEX

Explanations

sections labeled as abstracts in documents

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Content before "abstract:"

np_acts-logits-general · gemini-2.0-flash

abstract:

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MigrationBuilder

-0.90

expandindo

-0.74

 الرياضيه

-0.74

原始内容存档于

-0.69

OrBuilder

-0.69

__(/*!

-0.67

 MainAxisSize

-0.67

 Spraw

-0.67

 Modem

-0.66

DockStyle

-0.66

POSITIVE LOGITS

ab

0.40

吧

0.39

eab

0.38

 createState

0.38

migrationBuilder

0.37

IRR

0.37

 obje

0.37

0.36

呢

0.36

Objects

0.35

Activations Density 0.193%

sections labeled as abstracts in documents

Content before "abstract:"

abstract:

No Comments

No Known Activations